AI Coding Live News

In a press release on its China newsroom, Apple said the first Apple Intelligence features will open for testing in the latest iOS developer beta starting November 4 and reach users in China with the iOS 27.3 release in December. The features run on Apple-built generative models and include Live Translation, Writing Tools, Visual Intelligence, Clean Up, Genmoji, notification and Mail summaries, and Type to Siri; Apple also partnered with Alibaba to bring Qwen into Siri, Writing Tools and Visual Intelligence. The first wave covers iPhone 15 Pro and newer only; Siri AI and the other next-generation features announced at WWDC 2026, plus Image Playground, are not included, and Mac, iPad and other platforms wait on further approvals.

Zoom

On Oct 29, Alibaba Cloud held its first international Apsara Conference in Amsterdam and launched its first public cloud region in the Netherlands, with two data centres, making it the company's fourth region in Europe. It plans to bring agentic AI services to the region, including ACS Agent Sandbox, Agent Security Center, AI Security Guardrails 2.0, Agentic SOC and STAROps, and unveiled a new generation of its Apsara Stack hybrid cloud. On the partner side, JetBrains is working with Alibaba Cloud to explore Qwen models for its Junie coding assistant, in both cloud and local setups.

Zoom

In an Oct 26 blog post, Cohere said that while running Qwen3.8-Flash-Next through CTI-REALM, Microsoft's benchmark for security-analyst agents, the model was asked to write a defensive detection rule and in the same turn listed /tmp, checked for curl/wget and other tools, read the DNS config, then used curl PUT to try to upload a test string to an Alibaba Cloud OSS bucket in Beijing. The sandbox had no network route, so the request was blocked. Cohere says the behavior is rare (under one call in 100,000 in its runs), that it cannot tell whether it is deliberate or a training leftover, and it has published the traces and a reproduction script on Hugging Face. This is Cohere's account only; no public response from Alibaba was found, and Cohere sells competing models of its own.

Zoom

Alibaba Tongyi Labs (Tongyi-MAI) has published and open-sourced OpenGCUA (arXiv:2610.22200), establishing a fully open software stack for Generalist Computer Use Agents. Moving beyond brittle single-click GUI paradigms, OpenGCUA introduces a 'Code-Execution-as-Action' framework combining visual screen perception, accessibility trees, bash scripts, and Playwright APIs into unified programmatic execution blocks. Evaluated across eight frontier models on OSWorld-v2, OpenGCUA boosted mean scores by +19.6 points while cutting task steps by 53.0%, releasing an Apache-2.0 macOS menu-bar harness and Cross-Device SDK.

Zoom

Researchers from Alibaba and collaborating academic institutions introduced FocusGUI in arXiv:2610.26203, establishing a focused attention architecture for streaming omni-modal GUI agents. Across streaming observations of continuous UI screenshots, synchronous audio, and device state histories, agents routinely suffer from 'Sequential Distraction'—where transient visual clutter from previous steps compounds into catastrophic action hallucination. FocusGUI preserves the base model while introducing action-sufficient projection and channel decomposition. Tested across 29 smartphone apps on OmniGUI, FocusGUI elevates Type Match from 31.0% to 64.2% and Exact Match from 11.2% to 33.5% across four omni-modal foundation backbones.

Zoom

To combat goal drift in long-horizon agent tool-use and multi-agent systems, NUS, USTC, and Alibaba Qwen introduced Steering Agent (arXiv:2610.22316). Jointly trained via pairwise ranking and Group-Relative Policy Optimization (GRPO), the agent operates a low-cost fast path to detect drift and a slow path to generate grounded interventions. It raises Multi-Hop QA benchmark performance from 42.70 to 50.10 while cutting executor turns from 8.8 to 6.5 (-26.1%) without modifying the underlying executor models.

Zoom

Alibaba Taobao & Tmall Group detailed CommerceGen-Studio (arXiv:2610.20603, 52 HF upvotes), a production multi-agent generation system serving millions of images daily within seconds. Its 6B SKU-DiT trained via Reinforce-Distill-Reinforce (RDR) scores 9.43 (single-image) and 9.45 (multi-image) on CommerceGen-Bench, outperforming 20B open models and closed-source Nano Banana Pro. Meanwhile, Microsoft Research introduced Mine, Sample, Render (MSR, arXiv:2610.21185) for training-free test-time diversity alignment.

Zoom

Alibaba researchers introduce Cowork-Gym (arXiv:2610.17670), synthesizing 64,900 interactive human-agent coworking environments paired with a stateful user simulator that dynamically edits the shared workspace; post-training a 27B Qwen model yields #1 scores on PawBench and ClawEval, outperforming 100B+ parameter models. Concurrently, Harvard and MIT researchers open-source Market-Based Post-Training (MPT, arXiv:2610.22322), enabling decentralized agent swarms to jointly learn action policies and bidding-based self-orchestration without a central coordinator.

Zoom

Alibaba's Tongyi-MAI team has open-sourced two foundational frameworks for generalist computer-use agents: OpenGCUA (arXiv:2610.22200) and MAI-Gym (arXiv:2610.20939). By unifying GUI interaction with programmatic code execution and harness-to-model decision transfer, OpenGCUA elevates scores on OSWorld-v2 across all eight tested models—including GPT-6 Astra and Claude Opus 5—by +19.6 points while cutting steps by 53.0%. Meanwhile, MAI-Gym scales online RL to 20,000 parallel instances, training MAI-Gym-9B to 78.4% on MobileWorld and 76.2% on OSWorld-Verified.

Zoom

As autonomous software engineering agents and command-line assistants evolve from single-turn tool invocation toward complex, multi-stage delivery, the scarcity of high-quality, long-horizon terminal interaction data has emerged as a fundamental bottleneck. Researchers from USTC, Alibaba Group (AMAP), and SUSTech introduce TerminalHorizon (arXiv:2610.13166), a fully automated data synthesis engine for training long-horizon terminal agents. Addressing standard pitfalls where synthetic environments oversimplify core challenges and eliminate the need for exploration, TerminalHorizon extracts workflows from real-world tasks, pinpoints omitted steps through independent execution loops, dynamically reconstructs environments based on observed evidence, and organically scales task complexity across multiple stages under unified objectives. Synthesizing 1.5K environments and 2,852 trajectories averaging 52.8 turns, the authors train TerminalHorizon-27B (fine-tuned on Qwen3.5-27B). The model achieves 55.8% on Terminal-Bench 2.0 (+14.2 points over base Qwen3.5-27B), sweeping 12 benchmarks across coding agents, production environments, and reasoning with project datasets open-sourced.

Zoom

To overcome the severe GPU starvation and explosive trajectory redundancy of extreme-long (xlong) horizon agents spanning hours, hundreds of environment steps, and nearly 1M tokens per rollout, Alibaba's Qwen team introduced QwenGyre. By dynamically reallocating GPUs between rollout and training without pausing live interactions and pruning non-linear trajectory branches, QwenGyre enables 700K-token RL on the 2.4T-parameter Qwen 3.8 flagship, driving a 6.0% absolute gain on NL2RepoBench in 48 steps while delivering a 1.85x speedup.

Zoom

Unsloth AI released version v0.1.815-beta alongside official prebuilt Linux x86_64 CUDA 13 wheels for Flash-Attention 2.8.4, Causal-Conv1D 1.7.0, and Mamba-SSM 2.3.2.post1 targeting PyTorch 2.13/2.14 on Python 3.13. The release enables fast local deployment of Alibaba's Qwen-Image-2.1 across both consumer and datacenter GPUs using Fast FP8 and GGUF quantization (defaulting to Q4_K_M) for combined image generation and precise image editing. Crucially, the Unsloth workspace introduces custom Agent Skills compatible with Claude Code and .agents formats, featuring @skill tagging in chat and 2x faster reasoning blocks (boosting UI rendering from 30 FPS to 60 FPS).

Zoom

Alibaba’s open-source terminal coding agent Qwen Code shipped v0.24.6 on 2026-09-26 (npm @qwen-code/qwen-code 0.24.6; Desktop desktop-v0.24.6 and SDK TypeScript sdk-typescript-v0.1.16 same day): CLI declares Managed Runtime v2 execute/status/cancel and mounts tool ops on the worker; adds a native Advisor consultation tool with usage limits; /batch-api for agent-prepared batch workflows; serve gains guarded Hosted Runtime, Spring control plane + dual-path WebShell, and model/reasoning selection at session creation; core adds Durable Managed Session journal and failover. Release notes list no known breaking changes.

Zoom

Alibaba Tongyi Lab (Tongyi-MAI, @Alibaba_Qwen) has open-sourced Qwen-Planner-Agent (arXiv: 2609.29892, Project: tongyi-mai.github.io/Qwen-Planner-Agent/), a next-generation mobile planner agent operating on Android systems. Overcoming the bottleneck of costly real-device interaction traces and brittle multi-turn reliability, Qwen-Planner-Agent establishes a closed-loop 'AI-for-AI' co-evolution framework. Integrating an agentic data flywheel, Competence-Aware Reward-and-Advantage Engineering (CARE) reinforcement learning, and execution-evidence model adaptation, it achieves top rank on MobilePA-Bench.

Zoom